Unified Harness Protocol (UHP) is an open HTTP standard that standardizes how complete agent runtimes - called harnesses - connect to applications and surrounding modules. A harness is defined as a full agent loop that plans, invokes tools, edits files, and returns results; UHP makes those harnesses portable and interchangeable by providing a single contract for discovery, configuration, task submission, streaming progress, session continuation, artifact retrieval, errors, security, and more. It’s released under Apache‑2.0, requires no hosted service, and is explicitly designed so a client written to the spec will work with any conformant server regardless of where or how harnesses run.
The specification is normative and versioned, organized into thirteen chapters (architecture, lifecycle, harnesses, plugins, environments, memories, tasks, streaming, sessions, files, errors, security, schema) and accompanied by machine‑readable OpenAPI/JSON Schema definitions and a runnable conformance suite. UHP intentionally mirrors the OpenAI Responses API surface where useful - accepting a compatible subset and emitting Server‑Sent Events for streaming - while adding harness‑specific fields for jobs, sessions, files, cancellation, and metadata. Implementation guidance covers generating types from the schema, running conformance checks, and following governance/versioning rules so servers and clients can interoperate predictably.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Open weight models now process over 71.5% of tokens and account for nearly 23% of AI Gateway spend, quadrupling their share since June. Spending on open weight models has increased more than four times in three months, reflecting rapid adoption and shifting AI usage patterns. (vercel.com)
An AI system has successfully designed 16 new viruses, including bacteriophages. This breakthrough raises concerns about potential biosecurity risks. (cnn.com)
Flux 3 Image Klein is a 5.6 billion parameter open weights model for text-to-image generation, editing, and multi-reference creation. It offers high-quality, ground-connected images with efficient performance on consumer GPUs, enabling local and on-device use. (bfl.ai)
Yum! Brands has implemented AI in its restaurants, such as automating drive-thru orders, which has improved employee retention by making jobs easier. Despite public criticism of AI, company leaders see its benefits in increasing workplace satisfaction and efficiency. (fortune.com)
Transformers function as sophisticated memory systems that recall information via self-attention, minimizing interference and boosting capacity. Different neural layers, from linear maps to self-attention, are explained as various forms of memory storage and retrieval. (alexwang.ai)
Granite Switch 4.1 integrates chat, decision-making, and speech-to-text functions into a single endpoint, enhancing efficiency and speed. It features models optimized for safety, decision tasks, and transcription, all with reduced GPU requirements. (huggingface.co)
Today's best Hacker News stories, summarized and screenshotted, one email a day.